There is a large amount of low-quality data in the monitoring data of bridge cable dynamic response. The existing data detection research focuses on obviously abnormal data with abnormal time-domain waveforms. However, there is chaotic data in frequency-domain characteristics with normal time-domain waveforms in the monitoring data, which can’t accurately reflect the dynamic characteristics of bridge cables. Aiming at this problem, the existing abnormal data detection is extended to data quality evaluation, and obvious abnormal data and frequency-domain chaotic data are detected at the same time. The data quality evaluation method of bridge cable dynamic response monitoring is established by using a convolutional neural network (CNN) and data frequency-domain features. The implementation process includes: the time-domain data sequence is transformed into a power spectral density function (PSDF) by fast Fourier transform (FFT); the Gramian angular field (GAF) method is used to visualize the PSDF sequence, and a CNN model is built to evaluate the data quality automatically. Taking the cable acceleration monitoring data of a cable-stayed bridge as an example, the proposed method is validated. The results show that compared with the time-domain sequence detection method, the PSDF sequence detection method can better distinguish normal and pseudo-normal data, and has a higher evaluation accuracy; the accuracy of the CNN model, established by using the monitoring data of two sensors, to evaluate the quality of all 26 sensor monitoring data is above 94%. In addition, the evaluation model, established by this method, is applied to the monitoring data quality evaluation of another similar bridge with an accuracy of 95%.